Non-null ranking models. i

Ordinally invariant, i.e., rank, measures of association for bivariate populations are discussed, with emphasis on the probabilistic and operational interpretations of their population values. The three measures considered at length are the quadrant measure, Kendall's tau, and Spearman's rho. Relationships between these measures are discussed, as are connections between these measures and certain measures of association for cross classifications. Sampling theory is surveyed with special attention to the motivation for sample values of the measures. The historical development of ordinal measures of association is outlined. * This research was supported in part by the Statistics Branch, Office of Naval Research. Reproduction in whole or in part is permitted for any purpose of the United States Government. A large part of the work leading to this paper was done at the Department of Statistics, University of California, Berkeley. I would like to thank the following persons for their suggestions and c...

Ordinal Measures of Association

The population measures of association for cross classifications, discussed in the authors' prior publications, have sample analogues that are approximately normally distributed for large samples. (Some qualifications and restrictions are necessary.) These large sample normal distributions with their associated standard errors, are derived for various measures of association and various methods of sampling. It is explained how the large sample normality may be used to test hypotheses about the measures and about differences between them, and to construct corresponding confidence intervals. Numerical results are given about the adequacy of the large sample normal approximations. In order to facilitate extension of the large sample results to other measures of association, and to other modes of sampling, than those treated here, the basic manipulative tools of large sample theory are explained and illustrated.

Measures of Association for Cross Classifications III: Approximate Sampling Theory

The performance of two well-known bearing-only location techniques, the maximum likelihood (ML) and the Stansfield estimators, is examined. Analytical expressions are obtained for the bias and the covariance matrix of the estimation error, which permit performance comparison for any case of interest. It is shown that the Stansfield algorithm provides biased estimates even for large numbers of measurements, in contrast with the ML method. The RMS error of the Stansfield technique is not necessarily larger than the RMS of the ML technique. However, it is shown that the ML technique is superior to the Stansfield method when the number of measurements is large enough. Simulation results verify the predicted theoretical performance. >

H. E. Daniels

Papers

Rank Correlation and Population Models

The Theory of Position Finding

Note on Durbin and Stuart's Formula for E(RS)